def step(self, iteration: int, **kwargs: Any) -> None:
"""
Perform the appropriate action at the given iteration.
Args:
iteration (int): the current iteration, ranged in [0, max_iter-1].
kwargs (Any): extra data to save, same as in
:meth:`Checkpointer.save`.
"""
iteration = int(iteration)
additional_state = {"iteration": iteration}
additional_state.update(kwargs)
if (iteration + 1) % self.period == 0:
self.checkpointer.save("model_{:07d}".format(iteration), **additional_state)
if self.max_to_keep is not None:
self.recent_checkpoints.append(self.checkpointer.get_checkpoint_file())
# pyre-fixme[6]: Expected `int` for 1st param but got `Optional[int]`.
# pyre-fixme[6]: Expected `int` for 1st param but got `Optional[int]`.
if len(self.recent_checkpoints) > self.max_to_keep:
file_to_delete = self.recent_checkpoints.pop(0)
if PathManager.exists(
file_to_delete
) and not file_to_delete.endswith("model_final.pth"):
PathManager.rm(file_to_delete)
if iteration >= self.max_iter - 1: # pyre-ignore
self.checkpointer.save("model_final", **additional_state)
def test_bad_args(self) -> None:
with self.assertRaises(NotImplementedError):
PathManager.copy(
self._remote_uri,
self._remote_uri,
foo="foo" # type: ignore
)
with self.assertRaises(NotImplementedError):
PathManager.exists(self._remote_uri, foo="foo") # type: ignore
with self.assertRaises(ValueError):
PathManager.get_local_path(
self._remote_uri,
foo="foo" # type: ignore
)
with self.assertRaises(NotImplementedError):
PathManager.isdir(self._remote_uri, foo="foo") # type: ignore
with self.assertRaises(NotImplementedError):
PathManager.isfile(self._remote_uri, foo="foo") # type: ignore
with self.assertRaises(NotImplementedError):
PathManager.ls(self._remote_uri, foo="foo") # type: ignore
with self.assertRaises(NotImplementedError):
PathManager.mkdirs(self._remote_uri, foo="foo") # type: ignore
with self.assertRaises(ValueError):
PathManager.open(self._remote_uri, foo="foo") # type: ignore
with self.assertRaises(NotImplementedError):
PathManager.rm(self._remote_uri, foo="foo") # type: ignore
PathManager.set_strict_kwargs_checking(False)
PathManager.get_local_path(self._remote_uri, foo="foo") # type: ignore
f = PathManager.open(self._remote_uri, foo="foo") # type: ignore
f.close()
PathManager.set_strict_kwargs_checking(True)
def step(self, iteration: int, **kwargs: Any):
"""
Perform the appropriate action at the given iteration.
Args:
iteration (int): the current iteration, ranged in [0, max_iter-1].
kwargs (Any): extra data to save, same as in
:meth:`Checkpointer.save`.
"""
iteration = int(iteration)
additional_state = {"iteration": iteration}
additional_state.update(kwargs)
if (iteration + 1) % self.period == 0:
self.checkpointer.save("model_{:07d}".format(iteration),
**additional_state)
if self.max_to_keep is not None:
all_checkpoint_files = (
self.checkpointer.get_all_checkpoint_files())
all_checkpoint_files = [
item for item in all_checkpoint_files
if not item.endswith("model_final.pth")
]
all_checkpoint_files.sort()
files_to_delete = all_checkpoint_files[:-self.max_to_keep]
for file in files_to_delete:
if PathManager.exists(file):
PathManager.rm(file)
if iteration >= self.max_iter - 1:
self.checkpointer.save("model_final", **additional_state)
def test_rm(self):
with open(os.path.join(self._tmpdir, "test_rm.txt"), "w") as f:
rm_file = f.name
f.write(self._tmpfile_contents)
f.flush()
self.assertTrue(PathManager.exists(rm_file))
self.assertTrue(PathManager.isfile(rm_file))
PathManager.rm(rm_file)
self.assertFalse(PathManager.exists(rm_file))
self.assertFalse(PathManager.isfile(rm_file))
def clean_up_checkpoints(checkpoint_dir, n_keep=1):
checkpoints = glob(os.path.join(checkpoint_dir, "model_*.pth"))
checkpoints.sort()
checkpoints_to_delete = checkpoints[:-n_keep]
for checkpoint in checkpoints_to_delete:
try:
PathManager.rm(checkpoint)
except FileNotFoundError:
pass
def create_file_symlink(file1, file2):
"""
Simply create the symlinks for a given file1 to file2.
Useful during model checkpointing to symlinks to the
latest successful checkpoint.
"""
try:
if PathManager.exists(file2):
PathManager.rm(file2)
PathManager.symlink(file1, file2)
except Exception as e:
logging.info(f"Could NOT create symlink. Error: {e}")
def test_bad_args(self) -> None:
# TODO (T58240718): Replace with dynamic checks
with self.assertRaises(ValueError):
PathManager.copy(
self._tmpfile,
self._tmpfile,
foo="foo" # type: ignore
)
with self.assertRaises(ValueError):
PathManager.exists(self._tmpfile, foo="foo") # type: ignore
with self.assertRaises(ValueError):
PathManager.get_local_path(self._tmpfile,
foo="foo") # type: ignore
with self.assertRaises(ValueError):
PathManager.isdir(self._tmpfile, foo="foo") # type: ignore
with self.assertRaises(ValueError):
PathManager.isfile(self._tmpfile, foo="foo") # type: ignore
with self.assertRaises(ValueError):
PathManager.ls(self._tmpfile, foo="foo") # type: ignore
with self.assertRaises(ValueError):
PathManager.mkdirs(self._tmpfile, foo="foo") # type: ignore
with self.assertRaises(ValueError):
PathManager.open(self._tmpfile, foo="foo") # type: ignore
with self.assertRaises(ValueError):
PathManager.rm(self._tmpfile, foo="foo") # type: ignore
PathManager.set_strict_kwargs_checking(False)
PathManager.copy(
self._tmpfile,
self._tmpfile,
foo="foo" # type: ignore
)
PathManager.exists(self._tmpfile, foo="foo") # type: ignore
PathManager.get_local_path(self._tmpfile, foo="foo") # type: ignore
PathManager.isdir(self._tmpfile, foo="foo") # type: ignore
PathManager.isfile(self._tmpfile, foo="foo") # type: ignore
PathManager.ls(self._tmpdir, foo="foo") # type: ignore
PathManager.mkdirs(self._tmpdir, foo="foo") # type: ignore
f = PathManager.open(self._tmpfile, foo="foo") # type: ignore
f.close()
# pyre-ignore
with open(os.path.join(self._tmpdir, "test_rm.txt"), "w") as f:
rm_file = f.name
f.write(self._tmpfile_contents)
f.flush()
PathManager.rm(rm_file, foo="foo") # type: ignore
def rm(path: str) -> None:
if FVCorePathManager:
return FVCorePathManager.rm(path)
os.remove(path)
# Populate the img_paths and img_labels based on torchvision image folder file structure.
for label in label_paths:
label_path = os.path.join(split_path, label)
images = PathManager.ls(os.path.join(split_path, label))
print(f"{len(images)} examples found for { label }, { split }.")
total_split_examples += len(images)
for image in images:
img_path = os.path.join(label_path, image)
img_paths.append(img_path)
img_labels.append(label)
dataset_summary[split]["num_examples"] = total_split_examples
print(f"{ total_split_examples } found for { split } split \n")
# Remove the split .npy filelist if they exist and resave them..
image_path = os.path.join(args.output, f"{split}_images.npy")
PathManager.rm(image_path)
save_file(img_paths, image_path)
print(f"Saved { image_path }")
label_path = os.path.join(args.output, f"{split}_labels.npy")
PathManager.rm(label_path)
save_file(img_labels, label_path)
print(f"Saved { label_path }")
# Save dataset summary.
dataset_summary_path = os.path.join(args.output, "dataset_summary.json")
PathManager.rm(dataset_summary_path)
save_file(dataset_summary, dataset_summary_path)
def save_filelist_data(input_data, output_filepath):
# Remove the split .npy filelist if they exist and resave them.
if PathManager.exists(output_filepath):
PathManager.rm(output_filepath)
save_file(input_data, output_filepath)
